{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BNY7IO463EC7WYVN55FRUGISSS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"71c8106075c6f608ccd3558439152841b113b0ff50f168848c0477da1746b779","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T19:25:30Z","title_canon_sha256":"193517fc0cac61e056be58cd65286cd4eb4dfbe8d853128624a575680ee1e363"},"schema_version":"1.0","source":{"id":"2605.24709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24709","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24709v1","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24709","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"BNY7IO463EC7","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"BNY7IO463EC7WYVN","created_at":"2026-05-26T01:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"BNY7IO46","created_at":"2026-05-26T01:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:ba6f914a904e19348e4626988073161dea4cac542629488a770fbd075f1f1386","target":"graph","created_at":"2026-05-26T01:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.24709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Streaming reinforcement learning has emerged as an online learning paradigm that conforms to the restrictions of natural learning agents that process data incrementally, i.e. with a batch size of 1 and no replay buffer. While streaming RL has recently been shown to scale with deep function approximation with full observability, partially observable settings have remained out of reach. Truncated backpropagation through time collapses to a one-step gradient horizon under the streaming setting, and exact real-time recurrent learning is prohibitively expensive. We close this gap using recurrent tr","authors_text":"Aryaman Reddi, Carlo D'Eramo, Jan Peters, Noah Farr","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T19:25:30Z","title":"Streaming Reinforcement Learning under Partial Observability with Real-Time Recurrent Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24709","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9d7f0374fcef876728a55233bd66b7847f7716b69486f7f3ab20947277333e7c","target":"record","created_at":"2026-05-26T01:03:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"71c8106075c6f608ccd3558439152841b113b0ff50f168848c0477da1746b779","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T19:25:30Z","title_canon_sha256":"193517fc0cac61e056be58cd65286cd4eb4dfbe8d853128624a575680ee1e363"},"schema_version":"1.0","source":{"id":"2605.24709","kind":"arxiv","version":1}},"canonical_sha256":"0b71f43b9ed905fb62adef4b1a191294a48cc7e9781653c4ee48ddd06e494210","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b71f43b9ed905fb62adef4b1a191294a48cc7e9781653c4ee48ddd06e494210","first_computed_at":"2026-05-26T01:03:54.591037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:54.591037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nt6OPc0jMeZsN7mF5BbiZ/JOjqQ6HosWA2+T21ZFNvMU/189iYec0O8fynjnZOTJXH7/BOXL5wZlY7eA/O4IDw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:54.591857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d7f0374fcef876728a55233bd66b7847f7716b69486f7f3ab20947277333e7c","sha256:ba6f914a904e19348e4626988073161dea4cac542629488a770fbd075f1f1386"],"state_sha256":"9fd0cca0b703d711dd4b3829a329445c424052f9b840ae3b194cca972fb52be2"}